Strategic Classification Made Practical
arXiv:2103.01826
Abstract
Strategic classification regards the problem of learning in settings where users can strategically modify their features to improve outcomes. This setting applies broadly and has received much recent attention. But despite its practical significance, work in this space has so far been predominantly theoretical. In this paper we present a learning framework for strategic classification that is practical. Our approach directly minimizes the "strategic" empirical risk, achieved by differentiating through the strategic response of users. This provides flexibility that allows us to extend beyond the original problem formulation and towards more realistic learning scenarios. A series of experiments demonstrates the effectiveness of our approach on various learning settings.
References in corpus (18)
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- Actionable Recourse in Linear Classification
- The Disparate Effects of Strategic Manipulation
- Differentiable Convex Optimization Layers
- Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
- A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
- Learning with Differentiable Perturbed Optimizers
- On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learning
- Learning Strategy-Aware Linear Classifiers
- Outside the Echo Chamber: Optimizing the Performative Risk
- Equalizing Recourse across Groups
- Performative Prediction
- Performative Prediction in a Stateful World
- How to Learn when Data Reacts to Your Model: Performative Gradient Descent
- PAC-Learning for Strategic Classification
- Differentiating through Log-Log Convex Programs
- From Predictions to Decisions: Using Lookahead Regularization
- Information Discrepancy in Strategic Learning